Pushpendra Singh

Sangoshthi : Empowering Community Health Workers through Peer Learning in Rural India

The Healthcare system of India provides outreach services to the rural population with a key focus on the maternal and child health through its flagship program of Community Health Workers (CHWs). The program since its launch has reached a scale of over 900000 health workers across the country and observed significant benefits on the health indicators. However, traditional face to face training mechanisms face persistent challenge in providing adequate training and capacity building opportunities to CHWs which leads to their sub-optimal knowledge and skill sets. In this paper, we propose Sangoshthi, a low-cost mobile based training and learning platform that fits well into the environment of low-Internet access. Sangoshthi leverages the architecture that combines Internet and IVR technology to host real time training sessions with the CHWs having access to basic phones only. We present our findings of a four week long field deployment with 40 CHWs using both qualitative and quantitative methods. Sangoshthi offers a lively environment of peer learning that was well received by the CHW community and resulted into their knowledge gains (16%) and increased confidence levels to handle the cases. Our study highlights the potential of complementary training platforms that can empower CHWs in-situ without the need of additional infrastructure.

Revisiting selection of residential consumers for demand response programs

Electrical utilities depend on Demand Response programs to manage peak loads by incentivizing consumers to voluntarily curtail a portion of their load during a specified period. Utilities first categorize consumers based on their energy consumption patterns into different clusters and then request consumers of a particular cluster to participate in the demand response program. At a coarse level, clustering approaches do well, but we may not be able to correctly predict which clusters profile will fit that days power availability. We address this issue by examining the consistency of consumers consumption patterns across several consecutive days. We demonstrate that measuring consistency quantitatively helps to understand predictability of consumers energy consumption. In the rest of the paper, we provide details of our proposed consistency metric. Further, we propose a methodology to select a few consumers among the consistent ones such that they have a peak at the time specified by the demand response program. We validate our approach using real-world energy consumption data from residential buildings.

I have no peace of mind —psychosocial distress expressed by rural women living with HIV in India as part of a mobile health intervention—a qualitative study

This qualitative study assessed psychosocial concerns that rural women with HIV who had multiple psychosocial vulnerabilities were able to express and communicate during a mobile phone intervention delivered by nurses. The study is part of a pilot randomised controlled trial of an mHealth self-care intervention by nurses for women living with HIV in rural India. For the trial, 60 women were randomised to receive the mHealth intervention. All calls were recorded and call logs were maintained. Call logs of 59 women based on 1186 calls were scanned for psychosocial themes. Audio recordings of 400 calls rich in content were then transcribed and translated for analysis. Themes and subthemes were identified by two independent raters. Majority of the women had low literacy and more than half were widowed. Clinical depression was found in 18.6%. Of the 1186 call logs analysed, 932 calls had a record of at least one psychosocial concern and 493 calls recorded two psychosocial concerns. Some of the major themes that women discussed with nurses included worries about their own and their children’s future; loneliness; stigma; inadvertent disclosure; death and dying; abandonment by partner; financial difficulties; body image; poor social support; emotions such as sadness, guilt, and anger; and need for social services. Almost all expressed appreciation for the intervention. Findings indicate the usefulness of mHealth-based self-care interventions delivered by nurses in hard to reach women in low- and middle-income countries, especially those with multiple psychosocial vulnerabilities.

Automatic Annotation of Voice Forum Content for Rural Users and Evaluation of Relevance

Voice forums are an effective intervention medium for marginalized communities to access information in a structured and localized manner. Users actively contribute by posting questions and responses in the form of audio messages, and thereby help in enriching the voice forum content. In order to build an audio library using the voice forums to disseminate information, significant manual effort is needed in analyzing and curating the data. This is one of the key impediments to the successful implementation of voice forums for knowledge dissemination and training. In this paper, we explore the effectiveness of automated approaches to analyze and curate voice forum content in Hindi, a native language in the northern part of India. We study the use of standard techniques such as topic modeling and extractive summarization on Hindi speech transcripts (with WER of 67%) to cluster audios thematically and create summaries for individual audios respectively. These curated audios are used to build an IVR-based library for community health workers in rural India. We evaluated the relevance and preference of the automated annotation using a field trail. We find that the relevance perception varied between human and automatically generated annotations, but automatically generated summaries were still found to be useful to access the voice forum audios.

Is India ready for mental health apps (MHApps)? A quantitative-qualitative exploration of caregivers’ perspective on smartphone-based solutions for managing severe mental illnesses in low resource settings

Background Mobile application based delivery of psycho-social interventions may help reduce the treatment gap for severe mental illnesses (SMIs) and decrease the burden on caregivers. Apps developed in high income settings show effectiveness, but they suffer from lack of applicability in low resource scenarios due to the difference in technology penetration, affordability, and acceptance. Objective This study aimed to understand health technology usage, perceived needs, and acceptability of app based interventions in patients with SMIs to improve illness management and reduce caregiver burden. Methods The study was conducted in inpatient and outpatient settings of a tertiary care center in North India. A cross-sectional survey assessed smartphone and health app usage. Further, three focus group discussions evaluated the needs and apprehensions in using apps in management of SMIs. Results A total of 176 participants including 88 patients and 88 caregivers completed the survey. Smartphone ownership was similar to the national average (30%) in both caregivers (38.6%) and in patients (31.8%). Although subjects regularly used a third party app, health app usage was very low. Cost, unfamiliarity, and language were significant barriers to adoption. The focus group discussions provided insight into the various apprehensions of caregivers in using and in allowing patients to use smartphones and such apps. Caregivers wanted mobile apps for accessing information regarding services and resources available for people with SMI, and they felt such apps can be helpful if they could automate some of their routine caregiving activities. However, the significant difficulty was perceived in regards to the cost of the device, language of the medium, and unfamiliarity in using technology. Apprehensions that SMI patients might misuse technology, or damage the device were also prevalent. Conclusions The study systematically looks into the scope, design considerations and limitations of implementing a mobile technology based intervention for low resource settings. With only one-third of the patients and caregivers having access to smartphones and internet, parallel outreach strategies like IVRS should be actively considered while designing interventions. The difficulty of understanding and searching in a non-native language needs to be addressed. Hand holding of caregivers and frequent encouragement from treating doctors might significantly help in technology adoption and in surmounting the apprehensions related to using technology. To make the solution acceptable and useful to the already over-burdened caregivers, developers need to work closely with patients’ family members and follow a ground-up collaborative approach to app development. The scope of delivering mental health services through technology is immense in resource constrained settings like India, provided we, researchers, appreciate and accept the fact that in the varied landscape of a divergent economic, educational, and cultural milieu, a single solution will never suffice for all, and intervention modality matching with end user capacity will be of paramount importance in determining the success of the endeavor.

Want to reduce energy consumption?: don't depend on the consumers!

Motivating users to save energy is considered to be the holy grail of smart energy management. However, many studies have shown that changing user behavior from an energy standpoint is a very difficult problem. Furthermore, in countries such as the United States, users do not have sufficient monetary incentives to become energy conscious, given the low cost of electricity, and more generally, energy. In this paper, we study this issue in a developing economy and present a user study of 41 apartments in a high-rise apartment complex in India. Through a combination of fine-grain energy meter usage data and detailed user surveys, we find that these users may be no more energy conscious or motivated to adopt energy efficiency measures than their counterparts in Western nations. Our study challenges the belief that energy prices are higher in developing regions and hence, users in developing regions tend to be more energy-aware than those elsewhere. Consequently, and importantly, we argue that utility companies, rather than end-users, should be the vanguard for realizing energy efficiency improvement at consumer premises in order to obtain grid-wide benefits such as peak load reduction or avoiding blackouts. Towards this goal, we argue for a sustained research effort into utility-scale energy analytic approaches, for example, to identify end users who are large consumers along with the underlying causes of their consumption. Utilities can deploy such approaches and then aggressively target these users for energy efficiency improvements.

Energy disaggregation for identifying anomalous appliance

Energy disaggregation research claims that it can be used to identify anomalous appliances. Our study proposes a technique which checks how accurate is disaggregated data in identifying such appliances. The evaluation of proposed technique on four different homes shows that disaggregation enables to find anomalies in air conditioner and refrigerator with an average F-score of 0.35, which is low on a scale of 0 to 1.

Mew: A Plug-n-Play Framework for Task Allocation in Mobile Crowdsensing

Mobile CrowdSensing (MCS) applications rely on the availability of multiple mobile devices for collecting sensor data on a large scale. These applications are gaining popularity and are used in several domains such as environmental monitoring and traffic monitoring. Several frameworks have been proposed to facilitate the development of these applications which deal with specific issues such as energy harvesting and ensuring the privacy of users. An important challenge that remains unaddressed is the allocation of sensing tasks to users as per the application requirements. Existing frameworks impose pre-built task allocation schemes to automatically allocate tasks to a subset of participants which limits their applicability to a small set of applications. However, as the number of MCS applications is growing, there is a need to provide a flexible environment to the developers to support a larger set of task allocation algorithms. Towards this, we propose our framework - Mew - which offers plug-n-play functionality for implementing custom task allocation algorithms to allow developers to reach out to the required set of participants while solving other challenges associated with MCS application development (e.g., reliable communication and secure data exchange) in a black-box manner. We describe the design choices of Mew required to support plug-n-play functionality and demonstrate its usability by developing three proof-of-concept applications using different task allocation algorithms.